Nonlinear State Estimation Using Optimal Gaussian Sampling with Applications to Tracking
Abstract (englisch):
This thesis is concerned with the ubiquitous problem of estimating the hidden state of a discrete-time stochastic nonlinear dynamic system. The focus is on the derivation of new Gaussian state estimators and the improvement of existing approaches. Also the challenging task of distributed state estimation is addressed by proposing a sample-based fusion of local state estimates. The proposed estimation techniques are applied to extended object tracking.
| Zugehörige Institution(en) am KIT | Institut für Anthropomatik und Robotik (IAR) |
| Publikationstyp | Hochschulschrift |
| Publikationsjahr | 2018 |
| Sprache | Englisch |
| Identifikator | urn:nbn:de:swb:90-802858 KITopen-ID: 1000080285 |
| Verlag | Karlsruher Institut für Technologie (KIT) |
| Umfang | XIX, 154 S. |
| Art der Arbeit | Dissertation |
| Fakultät | Fakultät für Informatik (INFORMATIK) |
| Institut | Institut für Anthropomatik und Robotik (IAR) |
| Prüfungsdatum | 21.07.2017 |
| Schlagwörter | Nonlinear state estimation, Kalman filtering, distributed state estimation, target tracking, extended object tracking |
| Nachgewiesen in | OpenAlex |
| Referent/Betreuer | Hanebeck, U. |